© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 74141
    Prev
    Next
    INDEX
    Explanations

    terms and information related to income and taxes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tica
    -0.07
    antry
    -0.07
    antee
    -0.07
    arent
    -0.07
    inkle
    -0.06
    ean
    -0.06
    大åħ¨
    -0.06
    athers
    -0.06
     Nim
    -0.06
     Otto
    -0.06
    POSITIVE LOGITS
     income
    0.09
    income
    0.08
    beck
    0.07
     Income
    0.07
     earned
    0.07
    .receive
    0.07
     job
    0.06
     incomes
    0.06
     sources
    0.06
    æĶ¶åħ¥
    0.06
    Activations Density 0.035%

    No Known Activations